Plant disease diagnosis is essential to farmers' management choices because plant diseases frequently lower crop yield and product quality. For harvests to flourish and agricultural productivity to boost, grape leaf disease detection is important. The plant disease dataset contains grape leaf diseases total of 9,032 images of four classes, among them three classes are leaf diseases, and the other one is healthy leaves. After rigorous pre-processing dataset was split (70% training, 20% validation, 10% testing), and two pre-trained models were deployed: InceptionV3 and Xception. Xception shows a promising result of 96.23% accuracy, which is remarkable than InceptionV3. Adversarial Training is used for robustness, along with more transparency. Grad-CAM is integrated to confirm the leaf disease. Finally deployed a web application using Streamlit with a heatmap visualization and prediction with confidence level for robust grape leaf disease classification.
Reinforcement learning (RL), owing to its adaptability to various dynamic systems in many real-world scenarios and the capability of maximizing long-term outcomes under different constraints, has been used in infectious disease control to optimize the intervention strategies for controlling infectious disease spread and responding to outbreaks in recent years. The potential of RL for assisting public health sectors in preventing and controlling infectious diseases is gradually emerging and being explored by rapidly increasing publications relevant to COVID-19 and other infectious diseases. However, few surveys exclusively discuss this topic, that is, the development and application of RL approaches for optimizing strategies of non-pharmaceutical and pharmaceutical interventions of public health. Therefore, this paper aims to provide a concise review and discussion of the latest literature on how RL approaches have been used to assist in controlling the spread and outbreaks of infectious diseases, covering several critical topics addressing public health demands: resource allocation, balancing between lives and livelihoods, mixed policy of multiple interventions, and inter-regional coordinated control. Finally, we conclude the paper with a discussion of several potential directions for future research.
Diagnosing dental diseases from radiographs is time-consuming and challenging due to the subtle nature of diagnostic evidence. Existing methods, which rely on object detection models designed for natural images with more distinct target patterns, struggle to detect dental diseases that present with far less visual support. To address this challenge, we propose {\bf DentalX}, a novel context-aware dental disease detection approach that leverages oral structure information to mitigate the visual ambiguity inherent in radiographs. Specifically, we introduce a structural context extraction module that learns an auxiliary task: semantic segmentation of dental anatomy. The module extracts meaningful structural context and integrates it into the primary disease detection task to enhance the detection of subtle dental diseases. Extensive experiments on a dedicated benchmark demonstrate that DentalX significantly outperforms prior methods in both tasks. This mutual benefit arises naturally during model optimization, as the correlation between the two tasks is effectively captured. Our code is available at https://github.com/zhiqin1998/DentYOLOX.
The dynamic organization of chromatin plays a critical role in regulating muscle cell differentiation. Among the molecular elements influencing chromatin architecture, long noncoding RNAs (lncRNAs) have emerged as important regulators due to their capacity to act as scaffolds, recruiters of chromatin-modifying proteins, or as transcriptional enhancers. This review aims to explore the mechanisms by which lncRNAs influence chromatin structure in the context of skeletal muscle differentiation. We classified the functional roles of lncRNAs into three main strategies: recruitment of epigenetic modifiers, assembly of transcriptional scaffolds, and regulation through enhancer-like activity. We provide specific examples of lncRNAs associated with these mechanisms and discuss their involvement in the control of myogenic gene expression. These findings highlight the complexity and specificity of lncRNA-mediated chromatin remodeling and suggest their potential as targets for therapeutic intervention in muscle-related disorders.
Amr Abdelmonam A. Mostafa ElKatatny, Mahmoud Massoud, Atul Goel
et al.
Aim:
The authors report experience with 14 cases where two transfacet screws were used for transfacetal fixation of each joint for stabilization of the lumbar spinal segment and one transfacet screw was used for transfacetal fixation of each joint for stabilization of the cervical spinal segment. The anatomical subtleties of the technique of insertion of screws are elaborated.
Materials and Methods:
During the period from July 2024 to October 2024, 14 patients having spinal segmental vertical instability related to lumbar canal stenosis were treated in Helmya Military Hospital by insertion of screws into each articular assembly by transfacetal technique. We positioned the patient, then made a wide surgical exposure, and inserted the screws in an appropriate angulation.
Results:
During the period of follow-up, all treated patients had high patients’ satisfaction rate with relief of symptoms, and spinal levels showed firm bone fusion. There was no complication related to the insertion of the screws. There was no incidence of screw misplacement or implant rejection.
Conclusions:
Screw insertion into the firm and largely cortical bones of facets of the lumbar spine can provide robust fixation and firm stabilization of the spinal segment. The large size of the facets provides an opportunity to insert screws at each spinal segment. The firm and cortical bone material and absence of any neural or vascular structure in the course of the screw traverse provide strength and safety to the process.
Recent advances in artificial intelligence (AI) and multimodal data collection are revolutionizing dermatology. Generative AI and machine learning approaches offer opportunities to enhance the diagnosis and treatment of inflammatory skin diseases, including atopic dermatitis, psoriasis, hidradenitis suppurativa, and autoimmune connective tissue disease. This review examines the current landscape of AI applications for inflammatory skin diseases and explores how generative AI and machine learning methods can advance the field through deep phenotyping, disease heterogeneity characterization, drug development, personalized medicine, and clinical care. We discuss the promises and challenges of these technologies and present a vision for their integration into clinical practice.
Anthony Hevia, Sanjana Chintalapati, Veronica Ka Wai Lai
et al.
We present ROBOTO2, an open-source, web-based platform for large language model (LLM)-assisted risk of bias (ROB) assessment of clinical trials. ROBOTO2 streamlines the traditionally labor-intensive ROB v2 (ROB2) annotation process via an interactive interface that combines PDF parsing, retrieval-augmented LLM prompting, and human-in-the-loop review. Users can upload clinical trial reports, receive preliminary answers and supporting evidence for ROB2 signaling questions, and provide real-time feedback or corrections to system suggestions. ROBOTO2 is publicly available at https://roboto2.vercel.app/, with code and data released to foster reproducibility and adoption. We construct and release a dataset of 521 pediatric clinical trial reports (8954 signaling questions with 1202 evidence passages), annotated using both manually and LLM-assisted methods, serving as a benchmark and enabling future research. Using this dataset, we benchmark ROB2 performance for 4 LLMs and provide an analysis into current model capabilities and ongoing challenges in automating this critical aspect of systematic review.
Alzheimer's disease is not the outcome of a single cause but the convergence of many. This review reframes dementia as a systemic failure, where amyloid plaques and tau tangles are not root causes but late-stage byproducts of the underlying metabolic collapse. We begin by tracing the historical merger of early- and late-onset Alzheimer's into a single disease category, a conceptual error that may have misdirected decades of research. We then synthesize evidence pointing to metabolic dysfunction - especially mitochondrial damage - as a more likely initiating event. Through this lens, we examine diverse contributing factors including type 2 diabetes, hyperglycemia-induced oxidative stress, infections and neuroinflammation. Finally, we assess current treatment limitations and argue that prevention, grounded in early metabolic and vascular interventions, holds the most promise for altering the course of this complex disease.
Emilie Schurenberg, Edward M. Huddleston, Kenneth G. Saag
Primary care physicians (PCPs) play a critical role in the management of gout worldwide. However, significant gaps in gout care persist, underscoring the need for improved approaches to its management. While some guidelines, such as those from the American College of Physicians (ACP) published in 2016, support a more reactive treat-to-symptoms approach, others from the American College of Rheumatology (ACR) and the European Alliance Of Associations For Rheumatology advocate for a proactive treat-to-target (TTT) strategy—focused on achieving optimal serum urate levels through urate lowering therapy (ULT). This divergence reflects differing clinical priorities and differential interpretation of the evidence and it may contribute to variability in care delivery. Improving gout management requires greater engagement from both patients and healthcare providers, with particular emphasis on increasing adherence to ULT. Patients need enhanced support to better understand the importance of sustained urate lowering treatment, while healthcare providers may benefit from clearer guidance aligned with evidence-based strategies to foster greater patient trust and confidence. This article provides an overview of the current state of guidelines, highlights areas of agreement and discordance between them, and identifies key areas for improving care delivery. It additionally offers insight into alternative care delivery strategies, such as those involving non-physician health professionals, which have shown promise in enhancing patient outcomes. Future research should focus on continued development of innovative, multi-modal interventions to improve ULT adherence, including health system-based initiatives and collaborative care models.
Calcium pyrophosphate crystal deposition disease is a prevalent and impactful form of crystal arthropathy. It usually targets the large joints of the extremities, significantly affecting daily life. Progression of this disease, commonly observed in older individuals and often mistaken for septic arthritis, osteoarthritis, or several rheumatic conditions, remains poorly understood. The disease can present in various forms, from asymptomatic to severe joint deformity. The primary goal of treating this disease is to firmly control inflammation, prevent joint deformities, and decisively stop attacks. Medications used to treat the disease include anti-rheumatic drugs such as non-steroidal anti-inflammatory drugs, oral, intramuscular, or intra-articular steroids, hydroxychloroquine, colchicine, methotrexate, and interleukin-1 receptor antagonists. Radiosynovectomy is a radioactive technique that effectively targets and eliminates inflamed synovium. This article highlights the importance of awareness and early intervention to manage this condition effectively.
Systemic inflammatory rheumatic disorders are associated with an increased risk of malignancy. The mechanism linking malignancy and rheumatic diseases is complex and multidirectional, and is only partially understood. This review focused on the incidence of neoplastic diseases in patients with the most common systemic rheumatic disorders. Rheumatoid arthritis is associated with a risk of malignancy that is about 10% higher than in the general population, and this is more related to the disease itself than to medication. Systemic lupus erythematosus is associated with an increased risk of neoplasms, particularly haematological malignancies such as non-Hodgkin lymphoma. The risk increases with long-lasting active disease. Systemic sclerosis is associated with an increased risk of lung and liver cancer, as well as malignancies of the haematological system. Men and patients with RNA polymerase III antibodies are at a higher risk. Dermatomyositis and polymyositis are subgroups of idiopathic inflammatory myopathy associated with a high risk of malignancy. Male gender and old age are additional risk factors. Other rheumatic diseases are also thought to be associated with an increased risk of cancer. Currently, the data are insufficient for a clear distinction to be made between subgroups at risk. Most patients with systemic autoimmune disorders are at enhanced risk of malignancy to some degree. The management of these patients should include procedures for the early detection of age- and population-specific malignancies, as well as those which are more prevalent in the patient population suffering from the individual rheumatic disease. It is important to note that an atypical disease course or increased treatment resistance for a rheumatic disorder may indicate that the observed changes are an expression of a paraneoplastic syndrome or that a new neoplasm is modifying the clinical course of an already diagnosed rheumatic disease.
Kaileen Fei, Benjamin D. Andress, A’nna M. Kelly
et al.
AbstractMeniscus injuries are common and while surgical strategies have improved, there is a need for alternative therapeutics to improve long-term outcomes and prevent post-traumatic osteoarthritis. Current research efforts in regenerative therapies and tissue engineering are hindered by a lack of understanding of meniscus cell biology and a poorly defined meniscus cell phenotype. This study utilized bulk RNA-sequencing to identify unique and overlapping transcriptomic profiles in cartilage, inner and outer zone meniscus tissue, and passaged inner and outer zone meniscus cells. The greatest transcriptomic differences were identified when comparing meniscus tissue to passaged monolayer cells (> 4,600 differentially expressed genes (DEGs)) and meniscus tissue to cartilage (> 3,100 DEGs). While zonal differences exist within the meniscus tissue (205 DEGs between inner and outer zone meniscus tissue), meniscus resident cells are more similar to each other than to either cartilage or passaged monolayer meniscus cells. Additionally, we identified and validated LUM, PRRX1, and SNTB1 as potential markers for meniscus tissue and ACTA2, TAGLN, SFRP2, and FSTL1 as novel markers for meniscus cell dedifferentiation. Our data contribute significantly to the current characterization of meniscus cells and provide an important foundation for future work in meniscus cell biology, regenerative medicine, and tissue engineering.
Abstract Background It was reported the paraspinal muscle played an important role in spinal stability. The preoperative paraspinal muscle was related to S1 screw loosening. But the relationship between preoperative and postoperative change of psoas major muscle (PS) and S1 pedicle screw loosening in degenerative lumbar spinal stenosis (DLSS) patients has not been reported. This study investigated the effects of preoperative and follow-up variations in the psoas major muscle (PS) on the first sacral vertebra (S1) screw loosening in patients with DLSS. Methods 212 patients with DLSS who underwent lumbar surgery were included. The patients were divided into the S1 screw loosening group and the S1 screw non-loosening group. Muscle parameters were measured preoperatively and at last follow-up magnetic resonance imaging. A logistic regression analysis was performed to investigate the risk factors for S1 screw loosening. Results The S1 screw loosening rate was 36.32% (77/212). The relative total cross-sectional areas and relative functional cross-sectional areas (rfCSAs) of the PS at L2–S1 were significantly higher after surgery. The increased rfCSA values of the PS at L3–S1 in the S1 screw non-loosening group were significantly higher than those in the S1 screw loosening group. The regression analysis showed male, lower CT value of L1 and longer segment fusion were independent risk factors for S1 screw loosening, and postoperative hypertrophy of the PS was a protective factor for S1 screw loosening. Conclusions Compared to the preoperative muscle, the PS size increased and fatty infiltration decreased after surgery from L2–3 to L5–S1 in patients with DLSS after short-segment lumbar fusion surgery. Postoperative hypertrophy of the PS might be considered as a protective factor for S1 screw loosening. MRI morphometric parameters and postoperative selected exercise of PS for DLSS patients after posterior lumbar fusion surgery might contribute to improvement of surgical outcome.
Artificial intelligence applied to retinal images offers significant potential for recognizing signs and symptoms of retinal conditions and expediting the diagnosis of eye diseases and systemic disorders. However, developing generalized artificial intelligence models for medical data often requires a large number of labeled images representing various disease signs, and most models are typically task-specific, focusing on major retinal diseases. In this study, we developed a Fundus-Specific Pretrained Model (Image+Fundus), a supervised artificial intelligence model trained to detect abnormalities in fundus images. A total of 57,803 images were used to develop this pretrained model, which achieved superior performance across various downstream tasks, indicating that our proposed model outperforms other general methods. Our Image+Fundus model offers a generalized approach to improve model performance while reducing the number of labeled datasets required. Additionally, it provides more disease-specific insights into fundus images, with visualizations generated by our model. These disease-specific foundation models are invaluable in enhancing the performance and efficiency of deep learning models in the field of fundus imaging.
Abdelmalik Ouamane, Ammar Chouchane, Yassine Himeur
et al.
Machine learning has revolutionized the field of agricultural science, particularly in the early detection and management of plant diseases, which are crucial for maintaining crop health and productivity. Leveraging advanced algorithms and imaging technologies, researchers are now able to identify and classify plant diseases with unprecedented accuracy and speed. Effective management of tomato diseases is crucial for enhancing agricultural productivity. The development and application of tomato disease classification methods are central to this objective. This paper introduces a cutting-edge technique for the detection and classification of tomato leaf diseases, utilizing insights from the latest pre-trained Convolutional Neural Network (CNN) models. We propose a sophisticated approach within the domain of tensor subspace learning, known as Higher-Order Whitened Singular Value Decomposition (HOWSVD), designed to boost the discriminatory power of the system. Our approach to Tensor Subspace Learning is methodically executed in two phases, beginning with HOWSVD and culminating in Multilinear Discriminant Analysis (MDA). The efficacy of this innovative method was rigorously tested through comprehensive experiments on two distinct datasets, namely PlantVillage and the Taiwan dataset. The findings reveal that HOWSVD-MDA outperforms existing methods, underscoring its capability to markedly enhance the precision and dependability of diagnosing tomato leaf diseases. For instance, up to 98.36\% and 89.39\% accuracy scores have been achieved under PlantVillage and the Taiwan datasets, respectively.
Emre Koraman, Yusuf Iyetin, Oguzhan Ozyaman
et al.
Abstract Background Unstable femoral neck fractures with medial calcar defects are difficult to manage. The optimal fixation methods for these fractures have been a subject of ongoing debate among orthopedic surgeons. In this study, three different fixation techniques for vertical, medial defected femoral neck fractures were compared. Methods In this study, a biomechanical analysis was conducted to compare three fixation methods: cannulated screws (Group 1), cannulated screws combined with a medial buttress plate (Group 2), and intramedullary nails (Group 3). Synthetic composite bone models representing vertical collum femoris fractures with medial calcar defects were used. Each group consisted of seven specimens, and, to maintain consistency, a single surgeon performed the surgical procedure. Biomechanical testing involved subjecting the specimens to axial loading until failure, and the load to failure, stiffness, and displacement values were recorded. Normality was tested using the Shapiro–Wilk test. One-way ANOVA and Tukey’s HSD post hoc test were used for comparisons. Results The difference in the load to failure values was statistically significant among the groups, with Group 2 exhibiting the highest load to failure value, followed by Group 3 and Group 1. Stiffness values were significantly higher in Group 2 than in the other groups. Displacement values were not significantly different between the groups. Fracture and displacement patterns at the point of failure varied across the groups. Conclusion The results of this study indicate that fixation with a medial buttress plate in combination with cannulated screws provides additional biomechanical stability for vertical femoral neck fractures with medial calcar defects. Intramedullary nail fixation also demonstrated durable stability in these fractures. These findings can be used to better understand current management strategies for these challenging fractures to promote the identification of better evidence-based recommendations.
Orthopedic surgery, Diseases of the musculoskeletal system
Topic models have a rich history with various applications and have recently been reinvigorated by neural topic modeling. However, these numerous topic models adopt totally distinct datasets, implementations, and evaluations. This impedes quick utilization and fair comparisons, and thereby hinders their research progress and applications. To tackle this challenge, we in this paper propose a Topic Modeling System Toolkit (TopMost). Compared to existing toolkits, TopMost stands out by supporting more extensive features. It covers a broader spectrum of topic modeling scenarios with their complete lifecycles, including datasets, preprocessing, models, training, and evaluations. Thanks to its highly cohesive and decoupled modular design, TopMost enables rapid utilization, fair comparisons, and flexible extensions of diverse cutting-edge topic models. Our code, tutorials, and documentation are available at https://github.com/bobxwu/topmost.
Diffuse idiopathic skeletal hyperostosis (DISH) is a systemic condition characterized by the new bone formation and enthesopathies of the axial and peripheral skeleton. The diagnosis of DISH currently relies upon the end-stage radiographic criteria of Resnick and Niwayama, in which bridging osteophytes are present over at least four thoracic vertebras. The pathogenesis of DISH is not well understood, and it is currently considered a non-inflammatory condition with an underlying metabolic derangement. However, an inflammatory component was suggested due to the similarities between DISH and spondyloarthritis (SpA) in spinal and peripheral entheseal new bone formation. Magnetic resonance imaging (MRI) is the imaging modality of choice in the diagnostic work-up and follow-up of patients with SpA, as well as in understanding its pathogenesis. The aims of the current review were to evaluate the current and future role of MRI in imaging DISH.